获取已Hook函数的调用记录（包含参数和返回值）
AI agents call runtime_get_hook_logs to retrieve information from Js Reverse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns historical data (logs of hooked function calls, parameters, and return values) for analysis purposes. It performs passive observation of execution traces without creating, modifying, deleting, or executing new operations. In the context of reverse engineering, retrieving execution logs is a read-only forensic activity. No side effects on the analyzed system are induced by fetching logs.
From the tool's definition Tool name and description indicate retrieval of hook logs: 'runtime_get_hook_logs' retrieves 'Hook函数的调用记录' (hooked function call records including parameters and return values).
Attacks that exploit this kind of access
获取已Hook函数的调用记录（包含参数和返回值）. It is categorised as a Read tool in the Js Reverse MCP Server, which means it retrieves data without modifying state.
Register the Js Reverse MCP server in PolicyLayer and add a rule for runtime_get_hook_logs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Js Reverse. Nothing to install.
runtime_get_hook_logs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the runtime_get_hook_logs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for runtime_get_hook_logs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
runtime_get_hook_logs is provided by the Js Reverse MCP server (jenn619/js-reverse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →